Christian Theobalt

114

Papers

105

Total Citations

Papers (114)

HTML: A Parametric Hand Texture Model for 3D Hand Reconstruction and Personalization

Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input

HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View Synthesis

Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space

Bring Your Rear Cameras for Egocentric 3D Human Pose Estimation

FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video

BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects

Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels

CNS-Bench: Benchmarking Image Classifier Robustness Under Continuous Nuisance Shifts

OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects

NeurIPS 2025arXiv

3D Human Pose Perception from Egocentric Stereo Videos

Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras

VINECS: Video-based Neural Character Skinning

Wonder3D: Single Image to 3D using Cross-Domain Diffusion

ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis

EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams

ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering

REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning

Semi-Supervised Learning With Explicit Relationship Regularization

Fast and Robust Hand Tracking Using Detection-Guided Optimization

Efficient ConvNet-Based Marker-Less Motion Capture in General Scenes With a Low Number of Cameras

Local High-Order Regularization on Data Manifolds

Face2Face: Real-Time Face Capture and Reenactment of RGB Videos

GANerated Hands for Real-Time 3D Hand Tracking From Monocular RGB

Self-Supervised Multi-Level Face Model Learning for Monocular Reconstruction at Over 250 Hz

DS*: Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problems

InverseFaceNet: Deep Monocular Inverse Face Rendering

LIME: Live Intrinsic Material Estimation

Video Based Reconstruction of 3D People Models

On Implicit Filter Level Sparsity in Convolutional Neural Networks

Learning to Reconstruct People in Clothing From a Single RGB Camera

FML: Face Model Learning From Videos

In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations

A Convex Relaxation for Multi-Graph Matching

HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation From a Single Depth Map

StyleRig: Rigging StyleGAN for 3D Control Over Portrait Images

A Quantum Computational Approach to Correspondence Problems on Point Sets

EventCap: Monocular 3D Capture of High-Speed Human Motions Using an Event Camera

Monocular Real-Time Hand Shape and Motion Capture Using Multi-Modal Data

DeepDeform: Learning Non-Rigid RGB-D Reconstruction With Semi-Supervised Data

DeepCap: Monocular Human Performance Capture Using Weak Supervision

MINA: Convex Mixed-Integer Programming for Non-Rigid Shape Alignment

Monocular Reconstruction of Neural Face Reflectance Fields

Quantum Permutation Synchronization

Learning Complete 3D Morphable Face Models From Images and Videos

Monocular Real-Time Full Body Capture With Inter-Part Correlations

Pose-Guided Human Animation From a Single Image in the Wild

High-Fidelity Neural Human Motion Transfer From Monocular Video

i3DMM: Deep Implicit 3D Morphable Model of Human Heads

Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks

f-SfT: Shape-From-Template With a Physics-Based Deformation Model

Neural Rays for Occlusion-Aware Image-Based Rendering

BEHAVE: Dataset and Method for Tracking Human Object Interactions

Disentangled3D: Learning a 3D Generative Model With Disentangled Geometry and Appearance From Monocular Images

Estimating Egocentric 3D Human Pose in the Wild With External Weak Supervision

Playable Environments: Video Manipulation in Space and Time

Physical Inertial Poser (PIP): Physics-Aware Real-Time Human Motion Tracking From Sparse Inertial Sensors

CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes

Regularized Vector Quantization for Tokenized Image Synthesis

F2-NeRF: Fast Neural Radiance Field Training With Free Camera Trajectories

Mofusion: A Framework for Denoising-Diffusion-Based Motion Synthesis

NeuralUDF: Learning Unsigned Distance Fields for Multi-View Reconstruction of Surfaces With Arbitrary Topologies

Scene-Aware Egocentric 3D Human Pose Estimation

EventNeRF: Neural Radiance Fields From a Single Colour Event Camera

Grid-Guided Neural Radiance Fields for Large Urban Scenes

A Versatile Scene Model With Differentiable Visibility Applied to Generative Pose Estimation

Context-Guided Diffusion for Label Propagation on Graphs

Real-Time Hand Tracking Under Occlusion From an Egocentric RGB-D Sensor

MoFA: Model-Based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction

Accelerated Gravitational Point Set Alignment With Altered Physical Laws

Tex2Shape: Detailed Full Human Body Geometry From a Single Image

Multi-Garment Net: Learning to Dress 3D People From Images

HiPPI: Higher-Order Projected Power Iterations for Scalable Multi-Matching

EventHands: Real-Time Neural 3D Hand Pose Estimation From an Event Stream

Gravity-Aware Monocular 3D Human-Object Reconstruction

Adaptive Surface Normal Constraint for Depth Estimation

Towards High Fidelity Monocular Face Reconstruction With Rich Reflectance Using Self-Supervised Learning and Ray Tracing

Q-Match: Iterative Shape Matching via Quantum Annealing

Estimating Egocentric 3D Human Pose in Global Space

Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video

Efficient and Differentiable Shadow Computation for Inverse Problems

Synthesis of Compositional Animations From Textual Descriptions

Imitator: Personalized Speech-driven 3D Facial Animation

Batch-based Model Registration for Fast 3D Sherd Reconstruction

WaveNeRF: Wavelet-based Generalizable Neural Radiance Fields

NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction

LiveHand: Real-time and Photorealistic Neural Hand Rendering

GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild

Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction

DEMEA: Deep Mesh Autoencoders for Non-Rigidly Deforming Objects

Occlusion-Aware Depth Estimation with Adaptive Normal Constraints

Neural Re-Rendering of Humans from a Single Image

Neural Dense Non-Rigid Structure from Motion with Latent Space Constraints

PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations

Neural Voice Puppetry: Audio-driven Facial Reenactment

Self-supervised Outdoor Scene Relighting

UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture

NeRF for Outdoor Scene Relighting

Neural Radiance Transfer Fields for Relightable Novel-View Synthesis with Global Illumination

HULC: 3D HUman Motion Capture with Pose Manifold SampLing and Dense Contact Guidance

BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-Scale Scene Rendering

NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors

EgoRenderer: Rendering Human Avatars From Egocentric Camera Images

Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures

Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with Neural Deformation Fields

Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis

EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild

VidSeg: Training-free Video Semantic Segmentation based on Diffusion Models

LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration

Neural Sparse Voxel Fields

A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis

NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction

DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis

Weakly Supervised 3D Open-vocabulary Segmentation